CLAIR and APO - a ContextualAI Collection

ContextualAI 's Collections

LMUnit

CLAIR and APO

updated Aug 14, 2024

Data and Models for the paper "Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment"

ContextualAI/ultrafeedback_clair_32k

Viewer • Updated Sep 17, 2024 • 29.1k • 18 • 4
ContextualAI/ultrafeedback_rlaif_32k

Viewer • Updated Aug 13, 2024 • 31.8k • 15 • 1
ContextualAI/ultrafeedback_rlaif-offpolicy_32k

Viewer • Updated Aug 13, 2024 • 29.1k • 11 • 1
ContextualAI/ultrafeedback_stronger-preferred_32k

Viewer • Updated Aug 13, 2024 • 29.1k • 15 • 1